A5047690835- Advanced Battery Technologies Research
- Soil Geostatistics and Mapping
- Reservoir Engineering and Simulation Methods
- Advanced Multi-Objective Optimization Algorithms
- Probabilistic and Robust Engineering Design
- Supply Chain and Inventory Management
- Fuel Cells and Related Materials
- Advanced Causal Inference Techniques
- Electric Vehicles and Infrastructure
- Statistical Methods in Clinical Trials
- Rough Sets and Fuzzy Logic
- Data Mining Algorithms and Applications
- Anomaly Detection Techniques and Applications
- Scheduling and Optimization Algorithms
- Advancements in Battery Materials
- Geological Modeling and Analysis
- Statistical Methods and Inference
- Gaussian Processes and Bayesian Inference
- Reliability and Maintenance Optimization
Total (France)
2019-2023
Centre de Mathématiques Appliquées
2022
École Polytechnique
2022
Stanford University
2008-2013
Probabilistic regression models typically use the Maximum Likelihood Estimation or Cross-Validation to fit parameters. These methods can give an advantage solutions that observations on average, but they do not pay attention coverage and width of Prediction Intervals. A robust two-step approach is used address problem adjusting calibrating Intervals for Gaussian Processes Regression. First, covariance hyperparameters are determined by a standard method. Leave-One-Out Coverage Probability...
The number of complex infrastructures in an industrial setting is growing and not immune to unexplained recurring events such as breakdowns or failure that can have economic environmental impact. To understand these phenomena, sensors been placed on the different track, monitor, control dynamics systems. causal study data allows predictive prescriptive maintenance be carried out. It helps appearance a problem find counterfactual outcomes better operate defuse event. In this paper, we...
Maintaining a balance between the supply and demand of products by optimizing replenishment decisions is one most important challenges in chain industry. This paper presents novel reinforcement learning framework called MARLIM, to address inventory management problem for single-echelon multi-products with stochastic demands lead-times. Within this context, controllers are developed through single or multiple agents cooperative setting. Numerical experiments on real data demonstrate benefits...
Abstract In the current era of big data and machine learning, a strong focus exists on prediction classification. industrial applications, however, many important questions are not about or classification; rather, they causal: if I change A, what will happen to B? Traditional regression techniques such as learning optimize predictions based correlations seen in robust tools for epidemiologists biostatisticians when evaluating efficacy new treatments medications using observational data....